© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 17047
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating or organizing content

    oai_token-act-pair · gpt-3.5-turbo

    commands or phrases related to the action of creating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffff
    -0.72
    speak
    -0.71
    govtrack
    -0.69
    far
    -0.68
    hoe
    -0.67
    esa
    -0.65
    CLOSE
    -0.63
    âĹ¼
    -0.63
    sorry
    -0.62
    hander
    -0.62
    POSITIVE LOGITS
     custom
    1.00
     shortcuts
    0.95
     folders
    0.94
     layouts
    0.93
     reusable
    0.92
     new
    0.88
     presets
    0.87
     temporary
    0.85
     backups
    0.85
     templates
    0.85
    Activations Density 0.127%

    No Known Activations